{"id":"https://openalex.org/W2130729839","doi":"https://doi.org/10.1093/bioinformatics/btl645","title":"Speeding up tandem mass spectrometry database search: metric embeddings and fast near neighbor search","display_name":"Speeding up tandem mass spectrometry database search: metric embeddings and fast near neighbor search","publication_year":2007,"publication_date":"2007-01-19","ids":{"openalex":"https://openalex.org/W2130729839","doi":"https://doi.org/10.1093/bioinformatics/btl645","mag":"2130729839","pmid":"https://pubmed.ncbi.nlm.nih.gov/17237061"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/5/612/49830035/bioinformatics_23_5_612.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/23/5/612/49830035/bioinformatics_23_5_612.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113845539","display_name":"Debojyoti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debojyoti Dutta","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, 1050 Childs Way, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, 1050 Childs Way, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, 1050 Childs Way, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, 1050 Childs Way, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.2468,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.92181702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"23","issue":"5","first_page":"612","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9405999779701233,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9405999779701233,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.04390000179409981,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6930945515632629},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6663286685943604},{"id":"https://openalex.org/keywords/rolling-hash","display_name":"Rolling hash","score":0.6346167325973511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6187597513198853},{"id":"https://openalex.org/keywords/k-independent-hashing","display_name":"K-independent hashing","score":0.5478886365890503},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4833316504955292},{"id":"https://openalex.org/keywords/database-search-engine","display_name":"Database search engine","score":0.46959009766578674},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4321567714214325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3860699534416199},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.38599109649658203},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33897194266319275},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3237247169017792},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2332095503807068},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2291950285434723}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6930945515632629},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6663286685943604},{"id":"https://openalex.org/C108546238","wikidata":"https://www.wikidata.org/wiki/Q4228982","display_name":"Rolling hash","level":5,"score":0.6346167325973511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187597513198853},{"id":"https://openalex.org/C187062812","wikidata":"https://www.wikidata.org/wiki/Q6322840","display_name":"K-independent hashing","level":5,"score":0.5478886365890503},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4833316504955292},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.46959009766578674},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4321567714214325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3860699534416199},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.38599109649658203},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33897194266319275},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3237247169017792},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2332095503807068},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2291950285434723},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010449","descriptor_name":"Peptide Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010449","descriptor_name":"Peptide Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010449","descriptor_name":"Peptide Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btl645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/5/612/49830035/bioinformatics_23_5_612.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17237061","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17237061","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl645","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl645","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/5/612/49830035/bioinformatics_23_5_612.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2130729839.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1543113652","https://openalex.org/W1561803476","https://openalex.org/W1981593008","https://openalex.org/W1987869696","https://openalex.org/W2013255353","https://openalex.org/W2023096047","https://openalex.org/W2026465178","https://openalex.org/W2053827324","https://openalex.org/W2059572899","https://openalex.org/W2079056345","https://openalex.org/W2097463865","https://openalex.org/W2139927267","https://openalex.org/W2157354442","https://openalex.org/W2162006472"],"related_works":["https://openalex.org/W1870428314","https://openalex.org/W1600184780","https://openalex.org/W2186134513","https://openalex.org/W1979795732","https://openalex.org/W2071572981","https://openalex.org/W2783286101","https://openalex.org/W2407340388","https://openalex.org/W2008159385","https://openalex.org/W2130729839","https://openalex.org/W3124563862"],"abstract_inverted_index":{"MOTIVATION:":[0],"Due":[1],"to":[2,35,82,117,124,142,155,229],"the":[3,18,25,44,110,128,139,157,172,179,187,191,195,260,288],"recent":[4],"advances":[5],"in":[6,17,24,50,73,79,127,210],"technology":[7],"of":[8,20,60,69,76,96,121,148,161,175,194,233,259,276,285,287,312],"mass":[9,304],"spectrometry,":[10],"there":[11],"has":[12],"been":[13,33],"an":[14],"exponential":[15],"increase":[16],"amount":[19],"data":[21,39,45,320],"being":[22],"generated":[23,71],"past":[26],"few":[27],"years.":[28],"Database":[29],"searches":[30,46],"have":[31],"not":[32],"able":[34],"keep":[36],"with":[37],"this":[38,87,102,199],"explosion.":[40],"Thus,":[41],"speeding":[42],"up":[43],"becomes":[47],"increasingly":[48],"important":[49],"mass-spectrometry-based":[51],"applications.":[52],"Traditional":[53],"database":[54,88,129],"search":[55],"methods":[56],"use":[57,138,226],"one-against-all":[58,111],"comparisons":[59],"a":[61,65,80,91,119,145,168,176,207,211,221,231],"query":[62,134],"spectrum":[63,135,170,189,193,217],"against":[64],"very":[66],"large":[67],"number":[68],"peptides":[70,126],"from":[72,86],"silico":[74],"digestion":[75],"protein":[77],"sequences":[78,150],"database,":[81],"filter":[83,256],"potential":[84],"candidates":[85],"followed":[89],"by":[90,220,272],"detailed":[92],"scoring":[93],"and":[94,171,190,224,315],"ranking":[95],"those":[97],"filtered":[98],"candidates.":[99],"RESULTS:":[100],"In":[101,291],"article,":[103],"we":[104,107,136,201,225,293],"show":[105,251,294],"that":[106,131,151,245,252,295],"can":[108,137,255,298],"avoid":[109],"comparisons.":[112],"The":[113,159,215],"basic":[114],"idea":[115],"is":[116,165,178,218,248],"design":[118],"set":[120,232],"hash":[122,140,163,173,234],"functions":[123,141,235],"pre-process":[125],"such":[130,308],"for":[132,241,302],"each":[133,162,204],"find":[143],"only":[144],"small":[146],"subset":[147],"peptide":[149,177,205],"are":[152,321],"most":[153,281],"likely":[154],"match":[156],"spectrum.":[158],"construction":[160],"function":[164],"based":[166],"on":[167],"random":[169,188,216,222,227],"value":[174],"normalized":[180],"shared":[181],"peak":[182],"counts":[183],"score":[184],"(cosine)":[185],"between":[186],"hypothetical":[192],"peptide.":[196],"To":[197],"implement":[198],"idea,":[200],"first":[202],"embed":[203],"into":[206],"unit":[208],"vector":[209],"high-dimensional":[212],"metric":[213],"space.":[214],"represented":[219],"vector,":[223],"vectors":[228],"construct":[230],"called":[236],"locality":[237],"sensitive":[238],"hashing":[239],"(LSH)":[240],"preprocessing.":[242],"We":[243,250],"demonstrate":[244],"our":[246,253,296],"mapping":[247],"accurate.":[249],"method":[254,297],"out":[257,274,284],">95.65%":[258],"spectra":[261,277,305,313],"without":[262],"missing":[263,279],"any":[264],"correct":[265,289],"sequences,":[266],"or":[267],"gain":[268],"111":[269],"times":[270],"speedup":[271],"filtering":[273],"99.64%":[275],"while":[278],"at":[280,323],"0.19%":[282],"(2":[283],"1014)":[286],"sequences.":[290],"addition,":[292],"be":[299],"effectively":[300],"used":[301],"other":[303],"mining":[306],"applications":[307],"as":[309],"finding":[310],"clusters":[311],"efficiently":[314],"accurately.":[316],"SUPPLEMENTARY":[317],"INFORMATION:":[318],"Supplementary":[319],"available":[322],"Bioinformatics":[324],"online.":[325]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}